© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10550
    Prev
    Next
    INDEX
    Explanations

    synthesis of / synthetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ged
    -0.18
    uster
    -0.18
    umen
    -0.17
    inding
    -0.16
    ãģĹãģı
    -0.16
    usters
    -0.16
    azer
    -0.16
    ependency
    -0.15
    USTER
    -0.15
    uset
    -0.15
    POSITIVE LOGITS
    äºĨä¸įå°ij
    0.21
    zed
    0.17
    оÑĢÑĤ
    0.17
    onyms
    0.16
    äºĨ许å¤ļ
    0.16
    alem
    0.16
    bred
    0.15
    ãģĤãĤĭç¨ĭ度
    0.15
    ä¸įæĿ¥
    0.15
    æ¾
    0.15
    Activations Density 0.045%

    No Known Activations